Recently, video generation has witnessed rapid advancements, drawing increasing attention to image-to-video (I2V) synthesis on mobile devices. However, the substantial computational complexity and slow generation speed of diffusion models pose significant challenges for real-time, high-resolution video generation on resource-constrained mobile devices. In this work, we propose MobileI2V, a 270M lightweight diffusion model for real-time image-to-video generation on mobile devices. The core lies in: (1) We analyzed the performance of linear attention modules and softmax attention modules on mobile devices, and proposed a linear hybrid architecture denoiser that balances generation efficiency and quality. (2) We design a time-step distillation strategy that compresses the I2V sampling steps from more than 20 to only two without significant quality loss, resulting in a 10-fold increase in generation speed. (3) We apply mobile-specific attention optimizations that yield a 2-fold speed-up for attention operations during on-device inference. MobileI2V enables, for the first time, fast 720p image-to-video generation on mobile devices, with quality comparable to existing models. Under one-step conditions, the generation speed of each frame of 720p video is less than 100 ms. Our code is available at: https://github.com/hustvl/MobileI2V.

翻译：近年来，视频生成技术取得了快速进展，移动设备上的图像到视频（I2V）合成日益受到关注。然而，扩散模型巨大的计算复杂度和缓慢的生成速度，对资源受限的移动设备实现实时高分辨率视频生成构成了显著挑战。本研究提出MobileI2V，一个270M参数的轻量级扩散模型，用于在移动设备上实现实时图像到视频生成。其核心创新在于：（1）我们分析了线性注意力模块与Softmax注意力模块在移动设备上的性能表现，并提出了一种平衡生成效率与质量的线性混合架构去噪器。（2）我们设计了一种时间步蒸馏策略，将I2V采样步数从20步以上压缩至仅需两步，且无明显质量损失，从而使生成速度提升10倍。（3）我们应用了针对移动设备的注意力优化技术，在设备端推理过程中使注意力操作速度提升2倍。MobileI2V首次实现了在移动设备上快速生成720p图像到视频，其质量与现有模型相当。在单步采样条件下，每帧720p视频的生成时间少于100毫秒。代码已开源：https://github.com/hustvl/MobileI2V。